vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server: tests - passkey - limit the number of max tokens to predix

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-03-02 14:38:08 +01:00
parent cf4c86ee20
commit f8773f759e
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/tests/features/passkey.feature
View file

@ -50,5 +50,5 @@ Feature: Passkey / Self-extend with context shift
Then <n_predicted> tokens are predicted matching <re_content> Then <n_predicted> tokens are predicted matching <re_content>
Examples: Examples:
| hf_repo | hf_file | n_ctx_train | ngl | n_batch | n_slots | n_ga | n_ga_w | n_junk | n_grp | i_pos | seed | n_keep | passkey | n_predicted | re_content | | hf_repo | hf_file | n_ctx_train | ngl | n_batch | n_slots | n_ga | n_ga_w | n_junk | n_grp | i_pos | seed | n_keep | passkey | n_predicted | re_content |
| TheBloke/phi-2-GGUF | phi-2.Q4_K_M.gguf | 2048 | 5 | 512 | 1 | 8 | 512 | 250 | 4 | 50 | 86 | 32 | 42 | -1 | .*42.* | | TheBloke/phi-2-GGUF | phi-2.Q4_K_M.gguf | 2048 | 5 | 512 | 1 | 8 | 512 | 250 | 4 | 50 | 86 | 32 | 42 | 5 | The passkey is 42\. |